The invention relates to the technical field of automobile intelligent cabin driver behavior detection, in particular to a dangerous driving behavior recognition method based on a convolutional neural network and a genetic algorithm. According to the method, firstly, a large amount of training data sets are shot, a model is trained by using calibrated data through an OODCI algorithm, and in this way, a large amount of data without labels are calibrated. In the process, the returned value is not only the label but also the credibility of the label, the data with higher credibility is selected to expand the training data set, and meanwhile, the sample is further enhanced and expanded, so that a large amount of data required by training is obtained. And then through combination of the convolutional neural network and the genetic algorithm, the speed and the accuracy are greatly improved. And finally, deploying to a domain controller of an automobile, detecting a driver in real time, displaying the current state of the driver through a central control touch screen, and if dangerous driving behaviors exist, performing appropriate reminding.

    本发明涉及汽车智慧座舱驾驶员行为检测技术领域,特别涉及一种基于卷积神经网络和遗传算法的危险驾驶行为识别方法。本发明首先通过拍摄大量训练数据集,通过OODCI算法,利用已经标定的数据来训练模型,以此方式来对大量没有标签的数据进行标定。在此过程中返回值不仅是标签还有标签的可信度,选取较高可信度的数据用来扩充训练数据集,同时对样本进一步增强扩充,从而获得训练所需要的大量数据。然后通过把卷积神经网络和遗传算法的结合,大大提高了速度和精确度。最后部署到汽车的域控制器上,对驾驶员进行实时的检测,通过中控触摸屏显示驾驶员当前状态,如有危险驾驶行为并基于合适的提醒。


    Access

    Download


    Export, share and cite



    Title :

    Dangerous driving behavior recognition method based on convolutional neural network and genetic algorithm


    Additional title:

    一种基于卷积神经网络和遗传算法的危险驾驶行为识别方法


    Contributors:
    LIU XINHUA (author) / LIU ZHENGGUANG (author) / XU TONG (author) / CAO RONGGE (author) / HAO JINGBIN (author) / HUA DEZHENG (author) / LIU XIAOFAN (author) / ZHOU HAO (author) / XU LINHAO (author)

    Publication date :

    2023-12-01


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06V / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Driving behavior primitive recognition method based on convolutional neural network fusion model

    ZHENG XUELIAN / CUI XIAOTONG / LI XIANSHENG et al. | European Patent Office | 2024

    Free access

    Dangerous driving behavior recognition system, method and device

    LI XIAOGANG / CHE SHUN / WANG JINCHANG | European Patent Office | 2024

    Free access

    SYSTEM AND METHOD FOR PREDICTING DANGEROUS DRIVING BEHAVIOR USING SPIKING NEURAL NETWORK

    IN SU LEE / HYUN SEOB LEE / HYUN JAE JANG | European Patent Office | 2023

    Free access

    DANGEROUS DRIVING DETERMINATION DEVICE, DANGEROUS DRIVING DETERMINATION METHOD, AND DANGEROUS DRIVING DETERMINATION PROGRAM

    SATO TAKAYUKI / KASUYA JUNICHI / NAKAMURA MASAHIRO et al. | European Patent Office | 2021

    Free access